From: Uros Bizjak Date: Sun, 15 Oct 2023 20:24:39 +0000 (+0200) Subject: x86/percpu: Rewrite arch_raw_cpu_ptr() to be easier for compilers to optimize X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=a048d3abae7c33f0a3f4575fab15ac5504d443f7;p=linux.git x86/percpu: Rewrite arch_raw_cpu_ptr() to be easier for compilers to optimize Implement arch_raw_cpu_ptr() as a load from this_cpu_off and then add the ptr value to the base. This way, the compiler can propagate addend to the following instruction and simplify address calculation. E.g.: address calcuation in amd_pmu_enable_virt() improves from: 48 c7 c0 00 00 00 00 mov $0x0,%rax 87b7: R_X86_64_32S cpu_hw_events 65 48 03 05 00 00 00 add %gs:0x0(%rip),%rax 00 87bf: R_X86_64_PC32 this_cpu_off-0x4 48 c7 80 28 13 00 00 movq $0x0,0x1328(%rax) 00 00 00 00 to: 65 48 8b 05 00 00 00 mov %gs:0x0(%rip),%rax 00 8798: R_X86_64_PC32 this_cpu_off-0x4 48 c7 80 00 00 00 00 movq $0x0,0x0(%rax) 00 00 00 00 87a6: R_X86_64_32S cpu_hw_events+0x1328 The compiler also eliminates additional redundant loads from this_cpu_off, reducing the number of percpu offset reads from 1668 to 1646 on a test build, a -1.3% reduction. Signed-off-by: Uros Bizjak Signed-off-by: Ingo Molnar Cc: Andy Lutomirski Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Josh Poimboeuf Cc: Uros Bizjak Cc: Sean Christopherson Link: https://lore.kernel.org/r/20231015202523.189168-1-ubizjak@gmail.com --- diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 60ea7755c0fea..915675f3ad605 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -56,9 +56,11 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm ("add " __percpu_arg(1) ", %0" \ + asm ("mov " __percpu_arg(1) ", %0" \ : "=r" (tcp_ptr__) \ - : "m" (__my_cpu_var(this_cpu_off)), "0" (ptr)); \ + : "m" (__my_cpu_var(this_cpu_off))); \ + \ + tcp_ptr__ += (unsigned long)(ptr); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else /* CONFIG_SMP */